19MID0020 Assignment-1

Importing the necessary libraries

library(ggplot2)

Need help? Try Stackoverflow: https://stackoverflow.com/tags/ggplot2

library(plotly)

Attaching package: ‘plotly’

The following object is masked from ‘package:ggplot2’:

    last_plot

The following object is masked from ‘package:stats’:

    filter

The following object is masked from ‘package:graphics’:

    layout

First 5 records

df = read.csv('Expectancy.csv', header = TRUE, sep = ",")
head(df)

Last 5 records

tail(df)

Data-type of every attribute

str(df)

'data.frame':   1704 obs. of  7 variables:
 $ X        : int  1 2 3 4 5 6 7 8 9 10 ...
 $ country  : chr  "Afghanistan" "Afghanistan" "Afghanistan" "Afghanistan" ...
 $ continent: chr  "Asia" "Asia" "Asia" "Asia" ...
 $ year     : int  1952 1957 1962 1967 1972 1977 1982 1987 1992 1997 ...
 $ lifeExp  : num  28.8 30.3 32 34 36.1 ...
 $ pop      : int  8425333 9240934 10267083 11537966 13079460 14880372 12881816 13867957 16317921 22227415 ...
 $ gdpPercap: num  779 821 853 836 740 ...

Attributes in the data-set

attr(x = df, which = "names")  

[1] "X"         "country"   "continent" "year"      "lifeExp"   "pop"       "gdpPercap"

summary(df)

       X            country           continent              year         lifeExp           pop              gdpPercap       
 Min.   :   1.0   Length:1704        Length:1704        Min.   :1952   Min.   :23.60   Min.   :6.001e+04   Min.   :   241.2  
 1st Qu.: 426.8   Class :character   Class :character   1st Qu.:1966   1st Qu.:48.20   1st Qu.:2.794e+06   1st Qu.:  1202.1  
 Median : 852.5   Mode  :character   Mode  :character   Median :1980   Median :60.71   Median :7.024e+06   Median :  3531.8  
 Mean   : 852.5                                         Mean   :1980   Mean   :59.47   Mean   :2.960e+07   Mean   :  7215.3  
 3rd Qu.:1278.2                                         3rd Qu.:1993   3rd Qu.:70.85   3rd Qu.:1.959e+07   3rd Qu.:  9325.5  
 Max.   :1704.0                                         Max.   :2007   Max.   :82.60   Max.   :1.319e+09   Max.   :113523.1  

Checking for NULL values

lapply(df,function(x) { 
  length(which(is.na(x)))
})

$X
[1] 0

$country
[1] 0

$continent
[1] 0

$year
[1] 0

$lifeExp
[1] 0

$pop
[1] 0

$gdpPercap
[1] 0

1. Choose a country and plot the life expectancy by year (both scatter and line plot)

df_india = subset(df,country =="India")
df_india

Scatter Plot

ggplot(df_india, aes(x=year, y=lifeExp)) + 
  geom_point(size = 3, color = "#0099f9") + 
    labs(
    title = "Life Expectancy vs Year",
    subtitle = "LifeExp - Expected number of years remaining for an individual at any given year ",
    caption = "Source: Expectancy dataset"
) +
    theme(
    plot.title = element_text(color = "#0099f9", size = 20, face = "bold", hjust = 0.5),
    plot.subtitle = element_text(size = 13, face = "bold", hjust = 0.5),
    plot.caption = element_text(face = "italic", hjust = 0)
)

Line Plot

fig = plot_ly(data = df_india, x = ~year, y = ~lifeExp,
              type = 'scatter', mode = 'lines',
              marker = list(size = 10,
              color = 'rgba(255, 182, 193, .9)',
              line = list(color = 'rgba(152, 0, 0, .8)',width = 2)))

fig <- fig %>% layout(title = 'Life Expectancy vs Year',
        yaxis = list(zeroline = FALSE),
        xaxis = list(zeroline = FALSE)
)

fig

A marker object has been specified, but markers is not in the mode
Adding markers to the mode...
A marker object has been specified, but markers is not in the mode
Adding markers to the mode...

2. Plot the life expectancy by year for five countries. (both scatter and line plot)

## Take out the five countries
df_5countries<-df[df$country %in% c('China', 'India', 'France', 'Poland', 'Serbia'), ]
head(df_5countries)

Scatter plot

fig = plot_ly(data = df_5countries, x = ~year, y = ~lifeExp, color=~country,
              marker = list(size = 10))

fig <- fig %>% layout(title = 'Life Expectancy vs Year',
        yaxis = list(zeroline = FALSE),
        xaxis = list(zeroline = FALSE)
)
fig

No trace type specified:
  Based on info supplied, a 'scatter' trace seems appropriate.
  Read more about this trace type -> https://plotly.com/r/reference/#scatter
No scatter mode specifed:
  Setting the mode to markers
  Read more about this attribute -> https://plotly.com/r/reference/#scatter-mode
No trace type specified:
  Based on info supplied, a 'scatter' trace seems appropriate.
  Read more about this trace type -> https://plotly.com/r/reference/#scatter
No scatter mode specifed:
  Setting the mode to markers
  Read more about this attribute -> https://plotly.com/r/reference/#scatter-mode

Line plot

ggplot(df_5countries, aes(x=year, y=lifeExp, color=country)) + 
  geom_line(size = 1) + 
    labs(
    title = "Life Expectancy by year for five countries.",
    caption = "Source: Expectancy dataset"
) +
    theme(
    plot.title = element_text(color = "#0099f9", size = 20, face = "bold", hjust = 0.5),
    plot.subtitle = element_text(size = 13, face = "bold", hjust = 0.5),
    plot.caption = element_text(face = "italic", hjust = 0)
)

#3. Plot the life expectancy of all the countries in Europe for any particular year.

## Take out Europian Continent
df_europe2007 = subset(df,continent =="Europe"&year==2007)
head(df_europe2007)

Bar Plot

fig = plot_ly(data = df_europe2007, x = ~country, y = ~lifeExp,
              marker = list(size = 10))

fig <- fig %>% layout(title = 'Life Expectancy in Europen Continent in 2007 by year',
        yaxis = list(zeroline = FALSE),
        xaxis = list(zeroline = FALSE)
)
fig

No trace type specified:
  Based on info supplied, a 'bar' trace seems appropriate.
  Read more about this trace type -> https://plotly.com/r/reference/#bar
No trace type specified:
  Based on info supplied, a 'bar' trace seems appropriate.
  Read more about this trace type -> https://plotly.com/r/reference/#bar